Search Results for author: Huan Xu

Found 68 papers, 6 papers with code

Interest-oriented Universal User Representation via Contrastive Learning

no code implementations18 Sep 2021 Qinghui Sun, Jie Gu, Bei Yang, Xiaoxiao Xu, Renjun Xu, Shangde Gao, Hong Liu, Huan Xu

Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model for each downstream application.

Contrastive Learning Representation Learning +1

Markdowns in E-Commerce Fresh Retail: A Counterfactual Prediction and Multi-Period Optimization Approach

no code implementations18 May 2021 Junhao Hua, Ling Yan, Huan Xu, Cheng Yang

In this paper, by leveraging abundant observational transaction data, we propose a novel data-driven and interpretable pricing approach for markdowns, consisting of counterfactual prediction and multi-period price optimization.

Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial training

no code implementations27 Jan 2021 Sebastian Pokutta, Huan Xu

We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods.

Multi-Agent Coverage in Urban Environments

1 code implementation17 Aug 2020 Shivang Patel, Senthil Hariharan, Pranav Dhulipala, Ming C Lin, Dinesh Manocha, Huan Xu, Michael Otte

We study multi-agent coverage algorithms for autonomous monitoring and patrol in urban environments.

Robotics

Understanding and Resolving Performance Degradation in Graph Convolutional Networks

1 code implementation12 Jun 2020 Kuangqi Zhou, Yanfei Dong, Kaixin Wang, Wee Sun Lee, Bryan Hooi, Huan Xu, Jiashi Feng

In this work, we study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.

Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective

no code implementations2 Jun 2020 Yifei Zhao, Yu-Hang Zhou, Mingdong Ou, Huan Xu, Nan Li

To maximize cumulative user engagement (e. g. cumulative clicks) in sequential recommendation, it is often needed to tradeoff two potentially conflicting objectives, that is, pursuing higher immediate user engagement (e. g., click-through rate) and encouraging user browsing (i. e., more items exposured).

Implicit Bias of Gradient Descent based Adversarial Training on Separable Data

no code implementations ICLR 2020 Yan Li, Ethan X. Fang, Huan Xu, Tuo Zhao

Specifically, we show that for any fixed iteration $T$, when the adversarial perturbation during training has proper bounded L2 norm, the classifier learned by gradient descent based adversarial training converges in direction to the maximum L2 norm margin classifier at the rate of $O(1/\sqrt{T})$, significantly faster than the rate $O(1/\log T}$ of training with clean data.

RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection

1 code implementation21 Feb 2020 Qingsong Wen, Kai He, Liang Sun, Yingying Zhang, Min Ke, Huan Xu

Periodicity detection is a crucial step in time series tasks, including monitoring and forecasting of metrics in many areas, such as IoT applications and self-driving database management system.

Anomaly Detection Time Series +1

Efficient Meta Learning via Minibatch Proximal Update

no code implementations NeurIPS 2019 Pan Zhou, Xiao-Tong Yuan, Huan Xu, Shuicheng Yan, Jiashi Feng

We address the problem of meta-learning which learns a prior over hypothesis from a sample of meta-training tasks for fast adaptation on meta-testing tasks.

Few-Shot Learning Few-shot Regression

Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs

1 code implementation17 Jul 2019 Adrian Rivera Cardoso, Jacob Abernethy, He Wang, Huan Xu

Finding the Nash Equilibrium (NE) of a two player zero-sum game is core to many problems in statistics, optimization, and economics, and for a fixed game matrix this can be easily reduced to solving a linear program.

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data

no code implementations7 Jun 2019 Yan Li, Ethan X. Fang, Huan Xu, Tuo Zhao

Specifically, we show that when the adversarial perturbation during training has bounded $\ell_2$-norm, the classifier learned by gradient descent based adversarial training converges in direction to the maximum $\ell_2$-norm margin classifier at the rate of $\tilde{\mathcal{O}}(1/\sqrt{T})$, significantly faster than the rate $\mathcal{O}(1/\log T)$ of training with clean data.

Bayesian Active Learning With Abstention Feedbacks

no code implementations4 Jun 2019 Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh, Binh Nguyen

We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate.

Active Learning General Classification

Large Scale Markov Decision Processes with Changing Rewards

no code implementations NeurIPS 2019 Adrian Rivera Cardoso, He Wang, Huan Xu

We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner.

A Unified Framework for Marketing Budget Allocation

no code implementations4 Feb 2019 Kui Zhao, Junhao Hua, Ling Yan, Qi Zhang, Huan Xu, Cheng Yang

In our approach, a semi-black-box model is built to forecast the dynamic market response and an efficient optimization method is proposed to solve the complex allocation task.

Decision Making

Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning

no code implementations NeurIPS 2019 Chao Qu, Shie Mannor, Huan Xu, Yuan Qi, Le Song, Junwu Xiong

To the best of our knowledge, it is the first MARL algorithm with convergence guarantee in the control, off-policy and non-linear function approximation setting.

Multi-agent Reinforcement Learning

RobustSTL: A Robust Seasonal-Trend Decomposition Algorithm for Long Time Series

1 code implementation5 Dec 2018 Qingsong Wen, Jingkun Gao, Xiaomin Song, Liang Sun, Huan Xu, Shenghuo Zhu

Based on the extracted trend, we apply the the non-local seasonal filtering to extract the seasonality component.

Anomaly Detection Time Series

Risk-Averse Stochastic Convex Bandit

no code implementations1 Oct 2018 Adrian Rivera Cardoso, Huan Xu

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse.

The Online Saddle Point Problem and Online Convex Optimization with Knapsacks

no code implementations21 Jun 2018 Adrian Rivera, He Wang, Huan Xu

We relate this problem to the online saddle point problem and establish $O(\sqrt{T})$ regret using a primal-dual algorithm.

Robust Hypothesis Testing Using Wasserstein Uncertainty Sets

no code implementations NeurIPS 2018 Rui Gao, Liyan Xie, Yao Xie, Huan Xu

We develop a novel computationally efficient and general framework for robust hypothesis testing.

Two-sample testing

Communication-Efficient Projection-Free Algorithm for Distributed Optimization

no code implementations20 May 2018 Yan Li, Chao Qu, Huan Xu

We demonstrate this advantage and show that the linear oracle complexity can be reduced to almost the same order of magnitude as the communication complexity, when the feasible set is polyhedral.

Distributed Optimization Matrix Completion

Projection-Free Algorithms in Statistical Estimation

no code implementations20 May 2018 Yan Li, Chao Qu, Huan Xu

Recently people have reduced the gradient evaluation complexity of FW algorithm to $\log(\frac{1}{\epsilon})$ for the smooth and strongly convex objective.

A Multi-State Diagnosis and Prognosis Framework with Feature Learning for Tool Condition Monitoring

no code implementations30 Apr 2018 Chong Zhang, Geok Soon Hong, Jun-Hong Zhou, Kay Chen Tan, Haizhou Li, Huan Xu, Jihoon Hong, Hian-Leng Chan

For fault diagnosis, a cost-sensitive deep belief network (namely ECS-DBN) is applied to deal with the imbalanced data problem for tool state estimation.

Representation Learning

Fast Global Convergence via Landscape of Empirical Loss

no code implementations13 Feb 2018 Chao Qu, Yan Li, Huan Xu

While optimizing convex objective (loss) functions has been a powerhouse for machine learning for at least two decades, non-convex loss functions have attracted fast growing interests recently, due to many desirable properties such as superior robustness and classification accuracy, compared with their convex counterparts.

General Classification

Adaptive Recurrent Neural Network Based on Mixture Layer

no code implementations24 Jan 2018 Kui Zhao, Yuechuan Li, Chi Zhang, Cheng Yang, Huan Xu

By leveraging the mixture layer, the proposed method can adaptively update states according to the similarities between encoded inputs and prototype vectors, leading to a stronger capacity in assimilating sequences with multiple patterns.

Learning Deep Mean Field Games for Modeling Large Population Behavior

no code implementations ICLR 2018 Jiachen Yang, Xiaojing Ye, Rakshit Trivedi, Huan Xu, Hongyuan Zha

We consider the problem of representing collective behavior of large populations and predicting the evolution of a population distribution over a discrete state space.

Reinforcement Learning under Model Mismatch

no code implementations NeurIPS 2017 Aurko Roy, Huan Xu, Sebastian Pokutta

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it.

Q-Learning

Bayesian Pool-based Active Learning With Abstention Feedbacks

no code implementations23 May 2017 Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh, Binh Nguyen

We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate.

Active Learning General Classification

Nearly second-order asymptotic optimality of sequential change-point detection with one-sample updates

no code implementations19 May 2017 Yang Cao, Liyan Xie, Yao Xie, Huan Xu

Our proof is achieved by making a connection between sequential change-point and online convex optimization and leveraging the logarithmic regret bound property of online mirror descent algorithm.

Change Point Detection

Fake News Mitigation via Point Process Based Intervention

no code implementations ICML 2017 Mehrdad Farajtabar, Jiachen Yang, Xiaojing Ye, Huan Xu, Rakshit Trivedi, Elias Khalil, Shuang Li, Le Song, Hongyuan Zha

We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model.

SAGA and Restricted Strong Convexity

no code implementations19 Feb 2017 Chao Qu, Yan Li, Huan Xu

SAGA is a fast incremental gradient method on the finite sum problem and its effectiveness has been tested on a vast of applications.

Linear convergence of SDCA in statistical estimation

no code implementations26 Jan 2017 Chao Qu, Huan Xu

In this paper, we consider stochastic dual coordinate (SDCA) {\em without} strongly convex assumption or convex assumption.

Outlier Robust Online Learning

no code implementations1 Jan 2017 Jiashi Feng, Huan Xu, Shie Mannor

We consider the problem of learning from noisy data in practical settings where the size of data is too large to store on a single machine.

Linear Convergence of SVRG in Statistical Estimation

no code implementations7 Nov 2016 Chao Qu, Yan Li, Huan Xu

SVRG and its variants are among the state of art optimization algorithms for large scale machine learning problems.

Online Nonnegative Matrix Factorization with General Divergences

no code implementations30 Jul 2016 Renbo Zhao, Vincent Y. F. Tan, Huan Xu

We develop a unified and systematic framework for performing online nonnegative matrix factorization under a wide variety of important divergences.

Image Denoising Shadow Removal

Online Collaborative Learning for Open-Vocabulary Visual Classifiers

no code implementations CVPR 2016 Hanwang Zhang, Xindi Shang, Wenzhuo Yang, Huan Xu, Huanbo Luan, Tat-Seng Chua

Leveraging on the structure of the proposed collaborative learning formulation, we develop an efficient online algorithm that can jointly learn the label embeddings and visual classifiers.

Accelerated Randomized Mirror Descent Algorithms For Composite Non-strongly Convex Optimization

no code implementations23 May 2016 Le Thi Khanh Hien, Cuong V. Nguyen, Huan Xu, Can-Yi Lu, Jiashi Feng

Avoiding this devise, we propose an accelerated randomized mirror descent method for solving this problem without the strongly convex assumption.

Adaptive Maximization of Pointwise Submodular Functions With Budget Constraint

no code implementations NeurIPS 2016 Nguyen Viet Cuong, Huan Xu

We study the worst-case adaptive optimization problem with budget constraint that is useful for modeling various practical applications in artificial intelligence and machine learning.

Active Learning

Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms

no code implementations ICLR 2018 Tom Zahavy, Bingyi Kang, Alex Sivak, Jiashi Feng, Huan Xu, Shie Mannor

As most deep learning algorithms are stochastic (e. g., Stochastic Gradient Descent, Dropout, and Bayes-by-backprop), we revisit the robustness arguments of Xu & Mannor, and introduce a new approach, ensemble robustness, that concerns the robustness of a population of hypotheses.

Online Crowdsourcing

no code implementations8 Dec 2015 Changbo Zhu, Huan Xu, Shuicheng Yan

With the success of modern internet based platform, such as Amazon Mechanical Turk, it is now normal to collect a large number of hand labeled samples from non-experts.

Online Gradient Descent in Function Space

no code implementations8 Dec 2015 Changbo Zhu, Huan Xu

In many problems in machine learning and operations research, we need to optimize a function whose input is a random variable or a probability density function, i. e. to solve optimization problems in an infinite dimensional space.

Subspace Clustering with Irrelevant Features via Robust Dantzig Selector

no code implementations NeurIPS 2015 Chao Qu, Huan Xu

This paper considers the subspace clustering problem where the data contains irrelevant or corrupted features.

Social Trust Prediction via Max-norm Constrained 1-bit Matrix Completion

no code implementations24 Apr 2015 Jing Wang, Jie Shen, Huan Xu

Social trust prediction addresses the significant problem of exploring interactions among users in social networks.

Matrix Completion

Efficient Online Minimization for Low-Rank Subspace Clustering

no code implementations28 Mar 2015 Jie Shen, Ping Li, Huan Xu

Low-rank representation~(LRR) has been a significant method for segmenting data that are generated from a union of subspaces.

Clustering from Labels and Time-Varying Graphs

no code implementations NeurIPS 2014 Shiau Hong Lim, Yudong Chen, Huan Xu

Our theoretical results cover and subsume a wide range of existing graph clustering results including planted partition, weighted clustering and partially observed graphs.

Graph Clustering

Online Optimization for Max-Norm Regularization

no code implementations NeurIPS 2014 Jie Shen, Huan Xu, Ping Li

The key technique in our algorithm is to reformulate the max-norm into a matrix factorization form, consisting of a basis component and a coefficients one.

Matrix Completion

Convex Optimization Procedure for Clustering: Theoretical Revisit

no code implementations NeurIPS 2014 Changbo Zhu, Huan Xu, Chenlei Leng, Shuicheng Yan

In this paper, we present theoretical analysis of SON~--~a convex optimization procedure for clustering using a sum-of-norms (SON) regularization recently proposed in \cite{ICML2011Hocking_419, SON, Lindsten650707, pelckmans2005convex}.

Distributed Robust Learning

no code implementations21 Sep 2014 Jiashi Feng, Huan Xu, Shie Mannor

We propose a framework for distributed robust statistical learning on {\em big contaminated data}.

Online Optimization for Large-Scale Max-Norm Regularization

no code implementations12 Jun 2014 Jie Shen, Huan Xu, Ping Li

Max-norm regularizer has been extensively studied in the last decade as it promotes an effective low-rank estimation for the underlying data.

Matrix Completion

Robust Subspace Segmentation with Block-diagonal Prior

no code implementations CVPR 2014 Jiashi Feng, Zhouchen Lin, Huan Xu, Shuicheng Yan

Most current state-of-the-art subspace segmentation methods (such as SSC and LRR) resort to alternative structural priors (such as sparseness and low-rankness) to construct the affinity matrix.

Face Clustering graph construction +1

Online PCA for Contaminated Data

no code implementations NeurIPS 2013 Jiashi Feng, Huan Xu, Shie Mannor, Shuicheng Yan

We consider the online Principal Component Analysis (PCA) for contaminated samples (containing outliers) which are revealed sequentially to the Principal Components (PCs) estimator.

Provable Subspace Clustering: When LRR meets SSC

no code implementations NeurIPS 2013 Yu-Xiang Wang, Huan Xu, Chenlei Leng

Sparse Subspace Clustering (SSC) and Low-Rank Representation (LRR) are both considered as the state-of-the-art methods for {\em subspace clustering}.

Reinforcement Learning in Robust Markov Decision Processes

no code implementations NeurIPS 2013 Shiau Hong Lim, Huan Xu, Shie Mannor

An important challenge in Markov decision processes is to ensure robustness with respect to unexpected or adversarial system behavior while taking advantage of well-behaving parts of the system.

Learning Multiple Models via Regularized Weighting

no code implementations NeurIPS 2013 Daniel Vainsencher, Shie Mannor, Huan Xu

We demonstrate the robustness benefits of our approach with some experimental results and prove for the important case of clustering that our approach has a non-trivial breakdown point, i. e., is guaranteed to be robust to a fixed percentage of adversarial unbounded outliers.

Generalization Bounds

Online Robust PCA via Stochastic Optimization

no code implementations NeurIPS 2013 Jiashi Feng, Huan Xu, Shuicheng Yan

Robust PCA methods are typically based on batch optimization and have to load all the samples into memory.

Stochastic Optimization

Noisy Sparse Subspace Clustering

no code implementations5 Sep 2013 Yu-Xiang Wang, Huan Xu

This paper considers the problem of subspace clustering under noise.

Scaling Up Robust MDPs by Reinforcement Learning

no code implementations26 Jun 2013 Aviv Tamar, Huan Xu, Shie Mannor

We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm.

Clustering Sparse Graphs

no code implementations NeurIPS 2012 Yudong Chen, Sujay Sanghavi, Huan Xu

We develop a new algorithm to cluster sparse unweighted graphs -- i. e. partition the nodes into disjoint clusters so that there is higher density within clusters, and low across clusters.

Stochastic Block Model

Improved Graph Clustering

no code implementations11 Oct 2012 Yudong Chen, Sujay Sanghavi, Huan Xu

We show that, in the classic stochastic block model setting, it outperforms existing methods by polynomial factors when the cluster size is allowed to have general scalings.

Graph Clustering Stochastic Block Model

Exact Subspace Segmentation and Outlier Detection by Low-Rank Representation

no code implementations8 Sep 2011 Guangcan Liu, Huan Xu, Shuicheng Yan

In this work, we address the following matrix recovery problem: suppose we are given a set of data points containing two parts, one part consists of samples drawn from a union of multiple subspaces and the other part consists of outliers.

Outlier Detection

Clustering Partially Observed Graphs via Convex Optimization

no code implementations25 Apr 2011 Yudong Chen, Ali Jalali, Sujay Sanghavi, Huan Xu

This paper considers the problem of clustering a partially observed unweighted graph---i. e., one where for some node pairs we know there is an edge between them, for some others we know there is no edge, and for the remaining we do not know whether or not there is an edge.

Stochastic Block Model

Matrix completion with column manipulation: Near-optimal sample-robustness-rank tradeoffs

no code implementations10 Feb 2011 Yudong Chen, Huan Xu, Constantine Caramanis, Sujay Sanghavi

Moreover, we show by an information-theoretic argument that our guarantees are nearly optimal in terms of the fraction of sampled entries on the authentic columns, the fraction of corrupted columns, and the rank of the underlying matrix.

Matrix Completion

Distributionally Robust Markov Decision Processes

no code implementations NeurIPS 2010 Huan Xu, Shie Mannor

We consider Markov decision processes where the values of the parameters are uncertain.

Robust PCA via Outlier Pursuit

1 code implementation NeurIPS 2010 Huan Xu, Constantine Caramanis, Sujay Sanghavi

Singular Value Decomposition (and Principal Component Analysis) is one of the most widely used techniques for dimensionality reduction: successful and efficiently computable, it is nevertheless plagued by a well-known, well-documented sensitivity to outliers.

Dimensionality Reduction Matrix Completion

Robust Regression and Lasso

no code implementations NeurIPS 2008 Huan Xu, Constantine Caramanis, Shie Mannor

We generalize this robust formulation to consider more general uncertainty sets, which all lead to tractable convex optimization problems.

Cannot find the paper you are looking for? You can Submit a new open access paper.